# robots.txt for romaindelfosse.fr

# Default — allow all
User-agent: *
Allow: /

# Content usage signals (draft-romm-aipref-contentsignals)
# search=yes : allow indexing for traditional & AI search
# ai-input=yes : allow citation/quoting in AI answers (aligns with llms.txt)
# ai-train=no : do not use content as training data
Content-Signal: search=yes, ai-input=yes, ai-train=no

# Disallow API
Disallow: /api/

# =============================================
# AI / LLM crawlers — explicit opt-in for search & citation
# =============================================
# This site explicitly welcomes citation in AI answers. Each bot is allowed
# at the protocol level; the training opt-out is signalled via Content-Signal
# above and the per-bot policy in /.well-known/agents.json.

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: DuckDuckBot
Allow: /

# =============================================
# Commercial SEO crawlers — keep but throttle
# =============================================
# These bots respect crawl-delay and cost CPU without bringing referral traffic.

User-agent: SemrushBot
Crawl-delay: 30

User-agent: AhrefsBot
Crawl-delay: 30

User-agent: MJ12bot
Crawl-delay: 30

User-agent: DataForSeoBot
Crawl-delay: 30

# =============================================
# Sitemaps
# =============================================
Sitemap: https://www.romaindelfosse.fr/sitemap.xml
Sitemap: https://www.romaindelfosse.fr/sitemap-images.xml

# =============================================
# AI / LLM bibliography (not part of robots spec — informational)
# =============================================
# Markdown synopsis  : https://www.romaindelfosse.fr/llms.txt
# Markdown index     : https://www.romaindelfosse.fr/llms-full.txt
# Knowledge graph    : https://www.romaindelfosse.fr/graph.json
# Agent skills       : https://www.romaindelfosse.fr/.well-known/agent-skills/index.json
# Agent contact      : https://www.romaindelfosse.fr/.well-known/agents.json
# Security contact   : https://www.romaindelfosse.fr/.well-known/security.txt